linux-kernel - [PATCH 11/29] mm: rcu safe vma freeing

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210430195232.30491-12-michel@lespinasse.org>
Date:   Fri, 30 Apr 2021 12:52:12 -0700
From:   Michel Lespinasse <michel@...pinasse.org>
To:     Linux-MM <linux-mm@...ck.org>,
        Linux-Kernel <linux-kernel@...r.kernel.org>
Cc:     Laurent Dufour <ldufour@...ux.ibm.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Matthew Wilcox <willy@...radead.org>,
        Rik van Riel <riel@...riel.com>,
        Paul McKenney <paulmck@...nel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Joel Fernandes <joelaf@...gle.com>,
        Andy Lutomirski <luto@...nel.org>,
        Michel Lespinasse <michel@...pinasse.org>
Subject: [PATCH 11/29] mm: rcu safe vma freeing

This prepares for speculative page faults looking up and copying vmas
under protection of an rcu read lock, instead of the usual mmap read lock.

Note - it might also be feasible to just use SLAB_TYPESAFE_BY_RCU when
creating the vm_area_cachep, but that's probably too subtle to consider here.

Signed-off-by: Michel Lespinasse <michel@...pinasse.org>
---
 include/linux/mm_types.h | 16 +++++++++++-----
 kernel/fork.c            | 13 +++++++++++++
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 70882e628908..024970635921 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -304,12 +304,18 @@ struct vm_userfaultfd_ctx {};
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
 
-	unsigned long vm_start;		/* Our start address within vm_mm. */
-	unsigned long vm_end;		/* The first byte after our end address
-					   within vm_mm. */
+	union {
+		struct {
+			/* VMA covers [vm_start; vm_end) addresses within mm */
+			unsigned long vm_start, vm_end;
 
-	/* linked list of VM areas per task, sorted by address */
-	struct vm_area_struct *vm_next, *vm_prev;
+			/* linked list of VMAs per task, sorted by address */
+			struct vm_area_struct *vm_next, *vm_prev;
+		};
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+		struct rcu_head vm_rcu;	/* Used for deferred freeing. */
+#endif
+	};
 
 	struct rb_node vm_rb;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 426cd0c51f9e..7c22bf2b1f9d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -369,9 +369,22 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	return new;
 }
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+static void __vm_area_free(struct rcu_head *head)
+{
+	struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
+						  vm_rcu);
+	kmem_cache_free(vm_area_cachep, vma);
+}
+#endif
+
 void vm_area_free(struct vm_area_struct *vma)
 {
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	call_rcu(&vma->vm_rcu, __vm_area_free);
+#else
 	kmem_cache_free(vm_area_cachep, vma);
+#endif
 }
 
 static void account_kernel_stack(struct task_struct *tsk, int account)
-- 
2.20.1